Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add JiuNian3219/architext --skill archi-code-surveygit clone --depth 1 https://github.com/JiuNian3219/architextWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jiunian3219/architext/archi-code-survey)<a href="https://agentmods.dev/skills/jiunian3219/architext/archi-code-survey"><img src="https://agentmods.dev/badge/skills/jiunian3219/architext/archi-code-survey.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.00755 |
| Opus 5 | $0.00020 | $0.00378 |
| Sonnet 5 | $0.00008 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
archi-code-survey scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invocation
- Auto-invoke: No, not triggered by model based on description.
- Trigger location: Only explicitly called via
[[SUBAGENT]]/[[NO-SUBAGENT]]in/archi.*protocols. - Execution context: When subagent supported must execute in independent subagent/independent context; only downgrade to inline Skill when no subagent.
- Boundary: Only return protocol-required structured artifacts, subsequent write, confirm and signoff handled by calling protocol.
Design Principles
- Thorough Discovery: Full read of all non-third-party business code (exclude node_modules/vendor/dist etc generated artifacts)
- Layered Recording: Core modules record flows in detail; shared logic record signatures and dependencies; pure utilities record signatures and purposes
- Large Module Throttling: When single module > 20 files, sort by import count for detailed read of top 10, rest only record export signatures
- Evidence-Based: Any conclusion must be based on code facts, do not fabricate without evidence
Execution Phases
1a Coarse Read
- Read project root config files (auto-detect type):
- Node.js: package.json, tsconfig.json
- Rust: Cargo.toml
- Go: go.mod
- Python: pyproject.toml, requirements.txt
- Java: pom.xml, build.gradle
- Other: Use root directory config files as reference
- Read README.md (if exists)
- Scan directory structure (complete depth)
- Infer project feature tags (ui / data / cli / lib / api)
- Identify entry files and core modules; build module dependency sketch following entry file's import chain
1b Fine Read
- For each feature module:
- Start from entry file, read layer by layer following import/call chain, cover main business logic
- Extract main flows (user operation → system processing → result)
- Record associated file paths and importedBy reverse relationships
- Large modules (> 20 files): Sort by importedBy count for detailed read of top 10, rest only record export signatures
- For shared/infrastructure code (utils, middleware, config) full read, record by tier:
- Medium tier (auth/validation/error-handling/permission): Responsibility + export function signatures + who depends on it
- Simple tier (format/slugify/logger/helpers): Function name + parameter signature + one-sentence purpose
- Both write to publicAPI field
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 66 lines · 41 tokens per session scan A 331f25bb99cd
archi-code-survey is a skill published in the GitHub repository JiuNian3219/architext (14 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 755 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ppt-orchestrator
A dispatcher for creating presentations, slide decks, long images, and weekly reports. It chooses a visual style and output format, then sends the work to a more specialised add-on.
zhongguose-html-skill
An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.
教程类H5-小红书小工具
A method for building offline, single-page course experiences for Xiaohongshu’s Mini Tools, which are interactive pages published inside the platform. It combines written lessons, generated illustrations, and JavaScript page switching in a constrained container.
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
wechat-delivery
A workflow for preparing WeChat Official Account articles, images, covers, and publishing files in Chinese. WeChat Official Accounts are channels used by organizations to publish articles to followers.
ai-image-to-pptx
A workflow that creates a set of related images with AI and places them into a real PowerPoint file. The resulting .pptx file can be opened and edited in PowerPoint, Keynote, or WPS.